|
|
@@ -80,12 +80,14 @@ def cal_score(df):
|
|
|
# score = sharerate * backrate * LOG(lastonehour_return+1) * K2
|
|
|
|
|
|
# 视频状态过滤
|
|
|
+ log_.info(f'initial_df count = {len(df)}')
|
|
|
video_ids = [int(video_id) for video_id in df['videoid']]
|
|
|
filtered_result = filter_video_status(video_ids=video_ids)
|
|
|
filter_videos = set(video_ids) - set(filtered_result)
|
|
|
filter_df = df[int(df['videoid']) in filter_videos]
|
|
|
df = df.append(filter_df)
|
|
|
df = df.drop_duplicates(['videoid'], keep=False)
|
|
|
+ log_.info(f'filtered_df count = {len(df)}')
|
|
|
# 计算score
|
|
|
df = df.fillna(0)
|
|
|
df['share_rate'] = df['lastonehour_share'] / (df['lastonehour_play'] + 1000)
|
liqian